Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     combustion
    -0.07
    efe
    -0.07
    安
    -0.07
    BUFFER
    -0.07
    iev
    -0.06
     creature
    -0.06
    Daemon
    -0.06
    Ve
    -0.06
     socially
    -0.06
     therapies
    -0.06
    POSITIVE LOGITS
    .Template
    0.07
    Installing
    0.07
    _same
    0.06
    (not
    0.06
    Waiting
    0.06
    (high
    0.06
    tabla
    0.06
     �
    0.06
     byla
    0.06
     jt
    0.06
    Act Density 0.011%

    No Known Activations